NVIDIA RTX: DLSS 4.5 for UE5 and Multilingual ACE update
NVIDIA released DLSS 4.5 as an Unreal Engine plugin with Dynamic Multi Frame Generation and expanded ACE multilingual models via NVIGI 1.6.
TL;DR
- 01NVIDIA released DLSS 4.5 as an Unreal Engine plugin with Dynamic Multi Frame Generation and expanded ACE multilingual models via NVIGI 1.6.
- 02The DLSS 4.5 plugin brings Dynamic Multi Frame Generation and a new 6x Multi Frame Generation mode; ACE adds small language and speech models that cover hundreds of languages and dialects.
- 03NVIDIA released three headline updates: the DLSS 4.5 Unreal Engine plugin, NVIGI SDK 1.6 with new multilingual ACE models, and the NvRTX 5.7.4 branch update for Unreal Engine.
NVIDIA announced on May 27, 2026 that it is extending the RTX toolset for game developers with three coordinated updates: DLSS 4.5 as an Unreal Engine plugin, expanded multilingual capabilities in NVIDIA ACE delivered via NVIGI 1.6, and a stability-focused NvRTX 5.7.4 release for Unreal Engine. The DLSS 4.5 plugin brings Dynamic Multi Frame Generation and a new 6x Multi Frame Generation mode; ACE adds small language and speech models that cover hundreds of languages and dialects.
What did NVIDIA release for game developers?
NVIDIA released three headline updates: the DLSS 4.5 Unreal Engine plugin, NVIGI SDK 1.6 with new multilingual ACE models, and the NvRTX 5.7.4 branch update for Unreal Engine. DLSS 4.5 for UE now supports Dynamic Multi Frame Generation, a 6x Multi Frame Generation mode, and the second-generation transformer for Super Resolution. NVIGI 1.6 includes Qwen 3.5 4B, a small language model supporting 201 languages and dialects, NVIDIA Riva Parakeet TDT 600M ASR for 25 languages, and Chatterbox Multilingual 500M supporting 24 languages. NvRTX 5.7.4 rebases to Unreal Engine 5.7.4 and fixes several RTX integration and stability issues.
How do DLSS 4.5 and the ACE multilingual models work for games?
DLSS 4.5 works as an Unreal Engine plugin built on Streamline that gives developers direct access to Super Resolution and Frame Generation features and updated APIs for integration. The plugin lets teams adopt features selectively, such as Ray Reconstruction or Dynamic Multi Frame Generation, and includes sample code and documentation to reduce integration time. ACE’s multilingual capabilities arrive as optimized, on-device models available through NVIGI 1.6; Qwen 3.5 4B provides low-latency, context-aware responses across 201 languages and dialects, while Riva Parakeet TDT 600M ASR handles speech recognition across 25 languages and Chatterbox Multilingual 500M supplies expressive voices in 24 languages. NVIGI 1.6 also enables quick prototyping by connecting to a locally running llama.cpp server.
What did the NvRTX 5.7.4 update change?
NvRTX 5.7.4 updates the NVIDIA RTX branch to Unreal Engine 5.7.4 and focuses on stability and compatibility for RTX features. The release addresses a shader compile fix for RTX Mega Geometry on non-DX12 platforms, makes stability and correctness improvements to Opacity Micro-Map (OMM), improves compatibility between Unreal Engine 5 Substrate materials and NvRTX rendering paths, resolves issues in the NvAPI integration, and refreshes integration and migration documentation.
Why it matters
Game developers get two practical benefits: better visual performance and more realistic, locally running AI characters. DLSS 4.5’s Dynamic Multi Frame Generation and the 6x mode aim to raise frame generation and upscaling options inside Unreal Engine projects while exposing a consistent plugin path to lower integration overhead. ACE’s multilingual models make it feasible to ship conversational NPCs that respond and speak across hundreds of languages without moving inference to the cloud, because the models are optimized for on-device performance via NVIGI 1.6. The NvRTX 5.7.4 fixes reduce integration friction for teams adopting these RTX features in UE5 titles.
What to watch
NVIDIA will demo a full on-device MetaHuman NPC pipeline at Unreal Fest 2026 and is hosting the session "Ready, Set, Action: Why Your Next NPC Should Be Their Own Method Actor" on June 17. Watch for public demos or sample projects from that session showing the LoRA-powered, on-device performances and the Action and Cut workflow described for refining NPC motivations and generating training data.
Written by The Brieftide · Source: NVIDIA
The Brieftide Daily · 06:00
Briefs like this one, in your inbox every morning.
Continue reading
More in Enterprise AI AdoptionMulti-Agent Orchestration for Enterprise AI: arXiv Paper
An arXiv paper (18 Jun 2026) evaluates DAG Plan and Execute versus ReAct across 208 enterprise scenarios and adds a Task Manager that cuts.
ChatGPT Enterprise: new spend controls and usage analytics
OpenAI added spend controls and usage analytics to ChatGPT Enterprise to help organizations manage costs and scale AI.
NEA's Tiffany Luck: AI IPOs, personal agents and ROI reckoning
NEA partner Tiffany Luck on AI IPOs, personal agents, and the tokenmaxxing-to-ROI shift in enterprise AI spend.
OpenAI Partner Network launch: $150M fund to scale enterprise AI
OpenAI commits $150M to a Partner Network to help global partners accelerate enterprise AI adoption, deployment and transformation.